System Online
Vinit Jangir
AI/ML & Full-Stack Engineer.
Architecting full-stack ecosystems and deploying high-performance AI models. Bridging the gap between raw data and kinetic logic.
AI & ML Systems
RAG architectures, face detection, predictive modeling — from research to production.
Cloud Infrastructure
Kubernetes, Docker, Terraform, AWS — systems engineering at undergraduate level.
Full-Stack Dev
React, FastAPI, Go — clean architecture that performs under real-world load.
Open Source
Contributing to pgmpy, sktime, Joomla — navigating 100K+ line codebases globally.
Technologies I work with daily
Engineering
Intelligence
& Scalable
Systems.
I'm Vinit Jangir — an AI/ML specialist and full-stack engineer at Polaris School of Technology (Degree by Medhavi Skills University). I specialize in building intelligent systems at the intersection of machine learning and production-grade infrastructure. My work spans the entire pipeline: from training predictive models and orchestrating RAG architectures, to containerizing services with Docker, deploying on Kubernetes, and provisioning cloud infrastructure with Terraform on AWS.
With a keen eye for system design and a deep understanding of algorithms, I architect solutions that don't just work — they scale. Whether it's building a real-time AI proctoring engine or contributing inference improvements to open-source ML libraries, I blend strategy, performance, and clean code to bring ideas to production. Let's build something that matters.
Why Python for DSA?
Algorithm Design · Competitive ProgrammingPython isn't my crutch — it's my scalpel. While others debate languages, I leverage Python's expressive syntax to prototype O(n log n) solutions in minutes, then validate them against thousands of edge cases. The result? Cleaner AI logic. When your preprocessing pipeline, your model inference, and your algorithmic optimizations all speak the same language, you eliminate translation overhead and ship faster.
Tech Stack
Tools I work with.
Infrastructure & DevOps — Systems Engineering
Kubernetes
Orchestration
Docker
Containers
AWS
Cloud Platform
Terraform
IaC
Linux
Systems & Bash
Redis
In-Memory
CI/CD
Pipelines
Nginx
Reverse Proxy
Languages
Python
DSA Mastery
Go
Scalable Backends
TypeScript
Type-Safe
JavaScript
Frontend & Node
SQL
Data & Queries
AI / ML
RAG
Retrieval-Aug Gen
Face Detection
Real-Time Vision
Predictive Modeling
ML Pipelines
FastAPI
API Framework
TensorFlow.js
Browser ML
Frontend
React
Component UI
Tailwind CSS
Utility-First
Framer Motion
Animation
Next.js
SSR Framework
Vite
Build Tool
Portfolio
What I've built.
Explore my recent projects — each one engineered to solve real problems with production-grade code.
Vision
AI Proctoring PlatformSituation
Educational institutions lack proctoring tools that balance security with student experience.
Action
Engineered real-time face detection via TensorFlow.js, fullscreen enforcement with tab-switch telemetry, and a configurable security engine. Built admin cockpit with React + Zustand, backed by FastAPI + SQLite. Deployed via Docker.
Result
Zero-compromise exam environment — live in production, monitoring concurrent sessions with instant anomaly flagging.
Flux Currency
Situation
Currency traders need fast, visually intuitive tracking without the bloat of traditional trading platforms.
Action
Architected real-time exchange rate fetching via REST APIs with intelligent polling. Implemented market analytics visualizations and mobile-first design.
Result
Production dashboard with sub-200ms first contentful paint. Packaged as Android APK.
Personal AI
🔧 In DevelopmentSituation
General-purpose AI assistants lack persistent memory and system-level integration. They forget context between sessions.
Task
Build a personal AI assistant with long-term memory, contextual awareness, and system automation.
Action
Architecting a RAG-based memory system with vector embeddings for persistent conversation history. Implementing automation via Python/Go.
Open Source
Contributing to the ecosystem.
Open source isn't a checkbox on my resume — it's how I sharpen my engineering instincts.
I've actively contributed to pgmpy, sktime, AIonDemand, and p5.js.
Navigating unfamiliar 100K+ line codebases at scale, shipping CI-validated patches, and communicating technical decisions asynchronously with distributed teams across time zones. This real-world exposure allows me to write cleaner, more maintainable code and understand the nuances of large ecosystem architectures.